Gaussian Process Lstm Recurrent Neural Network Language Models for Speech Recognition
Lists
Only you see this
Abstract
Recurrent neural network language models (RNNLMs) have shown superior performance across a range of speech recognition tasks. At the heart of all RNNLMs, the activation functions play a vital role to control the information flows and tracking longer history contexts that are useful for predicting the following words. Long short-term memory (LSTM) units are well known for such ability and thus widely used in current RNNLMs. However, the deterministic parameter estimates in LSTM RNNLMs are prone to over-fitting and poor generalization when given limited training data. Furthermore, the precise forms of activations in LSTM have been largely empirically set for all cells at a global level. In order to address these issues, this paper introduces Gaussian process (GP) LSTM RNNLMs. In addition to modeling parameter uncertainty under a Bayesian framework, it also allows the optimal forms of gates being automatically learned for individual LSTM cells. Experiments were conducted on three tasks: the Penn Treebank (PTB) corpus, Switchboard conversational telephone speech (SWBD) and the AMI meeting room data. The proposed GP-LSTM RNNLMs consistently outperform the baseline LSTM RNNLMs in terms of both perplexity and word error rate.
BibTeX
@inproceedings{lam2019gaussian,
author = {Max W. Y. Lam and Xie Chen and Shoukang Hu and Jianwei Yu and Xunying Liu and Helen Meng},
title = {{Gaussian Process Lstm Recurrent Neural Network Language Models for Speech Recognition}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2019},
doi = {10.1109/icassp.2019.8683660},
}Loading related content...